Criar template de um prompt
Criar template de um prompt identificando e extraindo variáveis
As APIs de ferramentas de prompt estão em uma prévia de pesquisa fechada. Solicite para participar da prévia de pesquisa fechada.
Antes de começar
As ferramentas de prompt são um conjunto de APIs para gerar e melhorar prompts. Diferentemente de nossas outras APIs, esta é uma API experimental: você precisará solicitar acesso, e ela não tem o mesmo nível de compromisso com suporte a longo prazo como outras APIs.
Essas APIs são similares ao que está disponível no Anthropic Workbench, e são destinadas para uso por outras plataformas e ambientes de engenharia de prompt.
Começando com o aprimorador de prompt
Para usar a API de geração de prompt, você precisará:
- Ter se juntado à prévia de pesquisa fechada para as APIs de ferramentas de prompt
- Usar a API diretamente, em vez do SDK
- Adicionar o cabeçalho beta
prompt-tools-2025-04-02
Esta API não está disponível no SDK
Criar template de um prompt
Headers
Optional header to specify the beta version(s) you want to use.
To use multiple betas, use a comma separated list like beta1,beta2 or specify the header multiple times for each beta.
Body
The prompt to templatize, structured as a list of message objects.
Each message in the messages array must:
- Contain only text-only content blocks
- Not include tool calls, images, or prompt caching blocks
Example of a simple text prompt:
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Translate hello to German"
}
]
}
]
Note that only contiguous user messages with text content are allowed. Assistant prefill is permitted, but other content types will cause validation errors.
The existing system prompt to templatize.
{
"system": "You are a professional English to German translator",
[...]
}
Note that this differs from the Messages API; it is strictly a string.
Response
The templatized prompt with variable placeholders.
The response includes the input messages with specific values replaced by variable placeholders. These messages maintain the original message structure but contain uppercase variable names in place of concrete values.
For example, an input message content like "Translate hello to German" would be transformed to "Translate {{WORD_TO_TRANSLATE}} to {{TARGET_LANGUAGE}}".
{
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Translate {{WORD_TO_TRANSLATE}} to {{TARGET_LANGUAGE}}"
}
]
}
]
}
The input system prompt with variables identified and replaced.
If no system prompt was provided in the original request, this field will be an empty string.
Usage information
A mapping of template variable names to their original values, as extracted from the input prompt during templatization. Each key represents a variable name identified in the templatized prompt, and each value contains the corresponding content from the original prompt that was replaced by that variable.
Example:
"variable_values": {
"WORD_TO_TRANSLATE": "hello",
"TARGET_LANGUAGE": "German"
}
In this example response, the original prompt – Translate hello to German – was templatized to Translate WORD_TO_TRANSLATE to TARGET_LANGUAGE, with the variable values extracted as shown.
Was this page helpful?